Implementation of a digital neuron with nonlinear activation function using Piecewise linear approximation technique

Proceedings of the International Conference on Microelectronics, ICM

Volumn , Issue , 2007, Pages 69-72

  Mishra, Amit ^a,d   Zaheeruddin, ^b   Raj, Krishna ^c  

^a GLA Institute of Technology and Management   (India)

^b JAMIA MILLIA ISLAMIA CENTRAL UNIVERSITY   (India)

^c HARCOURT BUTLER TECHNOLOGICAL INSTITUTE   (India)

^d DR A P J ABDUL KALAM TECHNICAL UNIVERSITY   (India)

Author keywords

Artificial neural network; Digital hardware implementation; Piecewise linear approximation; Sigmoid function

Indexed keywords

BACKPROPAGATION; FIELD PROGRAMMABLE GATE ARRAYS (FPGA); HARDWARE; MICROELECTRONICS; PIECEWISE LINEAR TECHNIQUES;

ACTIVATION FUNCTIONS; ARTIFICIAL NEURAL NETWORK; BASIC BUILDING BLOCKS; BUILDING BLOCKS; DESIGN METHODOLOGIES; DIGITAL HARDWARE IMPLEMENTATION; FPGA IMPLEMENTATIONS; NEURON ARCHITECTURES; NON-LINEAR ACTIVATION FUNCTIONS; NON-LINEAR FUNCTIONS; PIECEWISE LINEAR APPROXIMATION; SIGMOID FUNCTION; SIGMOIDAL FUNCTIONS; SIMULATION RESULTS;

NEURAL NETWORKS;

EID: 51849124204     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICM.2007.4497664     Document Type: Conference Paper

References (15)

1. th International conference on Microelectronics, Rabat, Morocco, October 29-31, 2001:189-192
2. Amin, H., Curtis, K.M., Hayes-Gill, B. R.,'Piecewise linear approximation applied to nonlinear function of a neural network', IEE Proc., Circuits devices Syst., Vol. 144,No. 6, December 1997
3. F. Distante, M.G. Sami, R. Stefanelli, G. Storti-Gajani,'A compact and fast silicon implementation for Layered Neural Nets', proc. International workshop on VLSI for Artificial Intelligence and Neural Networks, Oxford, UK, sept. 1990
4. Moritoshi Yasunaga et alii, "Design, fabrication and evaluation of a 5 inch wafer scale neural network LSI composed of 576 digital neurons", Proc. UCNN 90, pp.11-527, S.Diego, CA, USA, 1990
5. Myers, D.J., and Hutchinson, R.A.: 'Efficient implementation of piecewise linear activation function for digital VLSI neural networks', Elect. Lett., 1989, 25, (24), pp. 1662-1663
6. Allipi, C., and Storti-Gajani, G.: 'Simple approximation of sigmoidal functions: realistic design of digital neural networks capable of learning', Proc. IEEE Int. Synip. Circuits and Syst., 1991,pp. 1505-1508
7. C.Alippi, S.Bonfanti, GStorti-Gajani "Approximating Sigmoidal Functions for VLSI Implementation of Neural Nets", Proc. 1st International Workshop on Microelectronics for Neural Networks, pp. 165, Dortmund, Germany, 1990
8. Murray, A.F., Smith, A.V.W., and Butler, Z.F.: 'Bit-serial neural networks', Proc. IEEE Conf. on Neural InJormation Proc.Syst., 1987, pp. 573-583
9. Lipmann, R.P.: 'Introduction to computing with neural nets', IEEE ASSP Mag., 1987, 4, (2), pp. 4-22
10. Hush, D.R., and Home, B.G.: 'Progress in supervised neural networks: what's new since Lippmann?', IEEE Signal Process.Mug., 1993, 10, (1), pp. 8-39
11. Faiedh, H., Gafsi, Z., Torki, K., Besbes, K.: 'Digital hardware implementation of a neural network Used for classification', 16th International conference on Microelectronics, ICM-2004 proc, 6-8 December 2004,pp.551-554
12. Nordstrom, T., and Svenson, B.: 'Using and designing massively parallel computers for artificial neural networks', J.Parallel Distrib. Comput., 1992, 14, pp. 260-285
13. Sammut, K.M., and Jones, S.R.: 'Implementing nonlinear activation function in neural network emulators', Electron. Lett., 1991, 27, (12), pp. 1037-1038
14. Ouali, J., and Saucier, G.: 'Fast generation of neuro-ASICs',Proc. Int. Neural Networks Conf, 1990, 2, pp. 563-567
15. Deprettere, E., Dewilde, P., and Udo, P.: 'Pipelined CORDIC architectures for fast VLSI filtering and array processing', Proc. Inf. Conf Acoust., Speech, and Signal Proc., 1984, pp. 41.A.6.1-41.A.6.4